© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15259
    Prev
    Next
    INDEX
    Explanations

    effect, recovery, or symptoms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     пÑĢиÑıÑĤн
    -0.23
    ÑĩÑĢежден
    -0.22
     ÐIJлекÑģан
    -0.21
    медиÑĨинÑģк
    -0.20
    æĹłåħ³
    -0.20
    нибÑĥд
    -0.20
    индивид
    -0.19
    æĬķåħ¥
    -0.19
     TOO
    -0.19
    æĬĬæı¡
    -0.19
    POSITIVE LOGITS
    Ñįм
    0.21
    以æѤ
    0.20
    éĿŀ常éĢĤåIJĪ
    0.19
    ä»İèĢĮ
    0.19
     ÑģÑĤали
    0.19
    оÑĩнÑĭй
    0.19
    å½¢æĪIJ
    0.18
     ì¦ī
    0.18
    æŀģ大çļĦ
    0.18
    пов
    0.18
    Activations Density 0.291%

    No Known Activations